Coding Tools
Copilot API now tracks non-IDE tool usage
GitHub Changeloghigh confidence
Why it matters
- →Enterprises can now audit token usage from external coding agents like Claude Code and OpenCode.
- →Admins gain visibility into which non-IDE tools are driving Copilot costs and request volume.
- →The API distinguishes between user-selected and product-chosen models for better governance.
GitHub has updated its Copilot usage metrics API to include a totals_by_client array, enabling enterprise and organization owners to track model usage from tools outside standard IDEs. The update captures request counts, session data, and token usage for clients such as OpenCode, Claude Code, Codex, Zed, and JetBrains, addressing previous gaps where non-IDE traffic was unreported. Metrics are available in 1-day and 28-day reports for users with View Copilot Metrics permissions, distinguishing between user-selected, auto-chosen, and product-selected model modes. This addition allows administrators to monitor token consumption across the full spectrum of developer tools rather than relying solely on IDE telemetry.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1GitHub Copilot adds VS Code Agents metrics
GitHub Changelog · September 11, 2026 · Same story
- 2GitHub Copilot CLI adds agentic usage metrics
GitHub Changelog · September 17, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot metrics now name custom agents and MCPs
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.